CN111428670A - Face detection method, face detection device, storage medium and equipment - Google Patents
Face detection method, face detection device, storage medium and equipment Download PDFInfo
- Publication number
- CN111428670A CN111428670A CN202010243467.4A CN202010243467A CN111428670A CN 111428670 A CN111428670 A CN 111428670A CN 202010243467 A CN202010243467 A CN 202010243467A CN 111428670 A CN111428670 A CN 111428670A
- Authority
- CN
- China
- Prior art keywords
- face
- lifting
- detection model
- detection
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application discloses a face detection method, a face detection device, a storage medium and face detection equipment, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a face image of a user; detecting the face image through a face-lifting detection model obtained by pre-training, wherein the face-lifting detection model is obtained by training face images before and after face lifting of a plurality of users; and determining whether the user is face-lifting or not according to a first detection result output by the face-lifting detection model. The embodiment of the application can apply the face detection technology to the field of face-lifting identification, thereby expanding the application range of the face detection technology.
Description
Technical Field
The embodiment of the application relates to the technical field of image processing, in particular to a face detection method, a face detection device, a face detection storage medium and face detection equipment.
Background
The face detection technology is a technology for extracting features of a face in an image and detecting the face according to extracted feature data.
The face detection technology can be applied to face search or face comparison. For example, after the feature data is obtained, the feature data in the face feature library and the extracted feature data are matched one by one, and one or more face images similar to the feature data are found; or, a plurality of images of one face are obtained by using the face detection technology for a plurality of times, the images are subjected to feature extraction, and the extracted feature data are compared and inquired with feature data in a face feature library for a plurality of times to obtain a face comparison result.
Most of the existing face detection technologies are applied to the field of security verification, for example, people and certificates can be compared through face search, and identity authentication is performed through face comparison, so that the application range of the face detection technology is narrow.
Disclosure of Invention
The embodiment of the application provides a face detection method, a face detection device, a storage medium and face detection equipment, which are used for solving the problems that the face detection technology can only be applied to the aspect of security verification and is narrow in application range. The technical scheme is as follows:
in one aspect, a face detection method is provided, and the method includes:
acquiring a face image of a user;
detecting the face image through a face-lifting detection model obtained by pre-training, wherein the face-lifting detection model is obtained by training face images before and after face lifting of a plurality of users;
and determining whether the user is face-lifting or not according to a first detection result output by the face-lifting detection model.
In one aspect, a face detection apparatus is provided, the apparatus including:
the acquisition module is used for acquiring a face image of a user;
the face detection module is used for detecting the face images through a face-lifting detection model obtained by pre-training, and the face-lifting detection model is obtained by training the face images before and after face lifting of a plurality of users;
and the determining module is used for determining whether the user is face-lifting or not according to a first detection result output by the face-lifting detection model.
In one aspect, there is provided a computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the face detection method as described above.
In one aspect, a face detection device is provided, which includes a processor and a memory, where the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the face detection method as described above.
The technical scheme provided by the embodiment of the application has the beneficial effects that at least:
the face image of the user is obtained, and the face image is detected through the face-lifting detection model obtained through pre-training, and the face-lifting detection model is obtained through training according to the face images of the user before and after face lifting, so that the face-lifting detection model can detect whether the face in the face image is lifted up or not, a first detection result used for indicating whether the user lifts up or not is generated, and therefore the face detection technology can be applied to the field of face-lifting identification, and the application range of the face detection technology is expanded.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method of face detection according to an embodiment of the present application;
fig. 2 is a flowchart of a method of face detection according to another embodiment of the present application;
fig. 3 is a block diagram of a face detection apparatus according to still another embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application more clear, the embodiments of the present application will be further described in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method of a face detection method according to an embodiment of the present application is shown, where the face detection method can be applied to a face detection device. The face detection method can comprise the following steps:
In this embodiment, the face image may be an image obtained by shooting a face, or an image including a face extracted after performing face recognition on an image including a face, and the embodiment does not limit the manner of obtaining the face image.
The facial image of the user may include one facial image (e.g., a front facial image), or may include at least two facial images (e.g., a front facial image, a left facial image, a right facial image, etc.) obtained by shooting the same user from multiple shooting angles, and the embodiment is not limited.
And 102, detecting the face image through a face-lifting detection model obtained by pre-training, wherein the face-lifting detection model is obtained by training the face images of a plurality of users before and after face lifting.
The face-lift detection model may be obtained by training of the face detection device, or may be obtained by the face detection device from other devices.
When the face-lift detection model is obtained by face detection equipment training, the face detection equipment can obtain face images of a plurality of users before and after face lifting, then the model is established, and the face images are used for training the model to obtain the face-lift detection model. The training mode is described in detail below, and is not described herein again.
After the face-lifting detection model is obtained, the face detection device may input the obtained face image into the face-lifting detection model, and the face image is detected by the face-lifting detection model. The detection method is described in detail in the following, and is not described herein.
And 103, determining whether the user is face-lifting or not according to the first detection result output by the face-lifting detection model.
The face-lift detection model may output a first detection result, which may be used to indicate that the user is face-lift or not face-lift.
To sum up, the face detection method provided by the embodiment of the present application detects a face image by obtaining the face image of a user and then detecting the face image through a face-lifting detection model obtained by training in advance, and the face-lifting detection model is obtained by training face images before and after face lifting of a plurality of users, so that the face-lifting detection model can detect whether the face in the face image is lifted, and a first detection result for indicating whether the user is lifted is generated, and thus, the face detection technology can be applied to the field of face-lifting identification, and the application range of the face detection technology is expanded.
Please refer to fig. 2, which shows a flowchart of a method of face detection according to another embodiment of the present application, and the face detection method can be applied to a face detection device. The face detection method can comprise the following steps:
In this embodiment, the face image may be an image obtained by shooting a face, or an image including a face extracted after performing face recognition on an image including a face, and the embodiment does not limit the manner of obtaining the face image.
The facial image of the user may include one facial image (e.g., a front facial image), or may include at least two facial images (e.g., a front facial image, a left facial image, a right facial image, etc.) obtained by shooting the same user from multiple shooting angles, and the embodiment is not limited.
In this embodiment, the face-lift detection model may be obtained by training of the face detection device, or may be obtained by the face detection device from other devices.
When the face-lift detection model is trained by the face detection device, the method may further include: acquiring a training sample set, wherein each training sample in the training sample set comprises a face image and mark information of the same user before and after face-lifting, and the mark information is used for indicating at least one face-lifting part in the face image; and training the created model according to the training sample set to obtain the face-lifting detection model.
The training sample set comprises a plurality of groups of training samples, and each group of training samples comprises face images and mark information. The following description will first be made of a face image in a training sample.
The face images in a training sample may include at least one set of images taken at the same shooting angle before and after face-lifting. For example, the face image may include a front face image before face-lifting and a front face image after face-lifting. Because the feature description of the human face by using a single human face image has contingency, particularly the human face may have large posture change in the motion process, and the human face has multi-angle information of a three-dimensional space, the detection accuracy is hardly ensured only by the features extracted from the single human face image. Moreover, the face of the person after face-lifting is changed in multiple directions, and the face is not limited to the nose, the eyes, the lips and the like, and the corresponding parts of the side face can be changed. Therefore, a plurality of face images at a plurality of shooting angles can be set, and multi-azimuth information points can be extracted. Taking the three shooting angles of the front, the left side and the right side as an example, the face images in one training sample may include a front face image before face-lifting, a left side face image and a right side face image, and a front face image after face-lifting, a left side face image and a right side face image.
The facial images in the training sample set may be obtained by shooting with a camera or purchased from a website, and the embodiment does not limit the acquisition mode of the facial images.
After the face image is obtained, the position and size of the face need to be accurately calibrated in the face image. Moreover, because the original face image has interference, each face image in the training sample set needs to be preprocessed first. The pretreatment mode can include but is not limited to at least one of the following treatment modes: light compensation, gray scale transformation, histogram equalization, normalization, geometric correction, filtering, and sharpening.
The following describes the labeling information in the training sample. The mark information is used for indicating at least one face-lifting part in the face image, and the face-lifting part can include but is not limited to: forehead, eyelid, nose, cheek, chin, mouth. For example, a training sample includes face images before and after eye-lift, a training sample includes face photographs before and after jaw-lift, and the like.
After the training sample set is obtained, the face detection equipment can create a model, wherein the model comprises a multidirectional face detection algorithm and a face-lifting point algorithm; then, the face detection device can input the training sample set into the model, continuously perform learning optimization on the model by using a large amount of data, finally analyze the difference of characteristic data before and after face-lifting, and train the face-lifting detection model. Because the face-lifting detection model is obtained by training a large number of training sample sets, the subjectivity of face-lifting detection is reduced.
After the face-lifting detection model is obtained, the face detection device may input the obtained face image into the face-lifting detection model, and the face image is detected by the face-lifting detection model. When detecting, the human face image needs to be subjected to feature extraction. The feature extraction is a key step in face detection, because a face mainly comprises eyes, a forehead, a nose, ears, a chin, a mouth and other parts, and the parts and the structural relationship among the parts can be described by geometric features, in brief, the feature extraction refers to representing face information by some numbers, and the numbers are feature data to be extracted.
In this implementation, feature extraction is performed on the face image through the face-lifting detection model to obtain first feature data, which may include: when the face image comprises at least two face images with different shooting angles, extracting the characteristics of each face image through a face-lifting detection model; and fusing the feature data of each identical part in all the face images through the face-lifting detection model to obtain first feature data, wherein the first feature data comprises the feature data of a plurality of parts in the face of the user.
The face-lift detection model can extract the features of a plurality of face images in a training sample through a multi-azimuth detection algorithm, describe the mutual relation among the obtained feature data according to the feature invariance, and then fuse the feature data of the same part according to the mutual relation to obtain first feature data, wherein the first feature data can also be called balanced multi-azimuth feature data. For example, the face image includes a front face image, a left side face image, and a right side face image, and the face-lift detection model may process the three face images to obtain the first feature data.
Compared with the characteristic extraction of a single face image, the method has the advantages that the multidirectional characteristic extraction is carried out on a plurality of face images, the contingency of characteristic data can be reduced to a certain extent, and the accuracy of the characteristic data is improved.
It should be noted that, when training the face-lifting detection model, multi-directional feature extraction may be performed on the face images before and after face lifting, because the face has some invariant feature values, the extracted multi-directional feature data may be used to describe the correlation between the feature values according to the feature value invariant characteristic, so as to obtain the balanced feature values before and after face lifting, and the feature value template with the face lifting characteristic is obtained after normalization processing is performed on the two groups of balanced feature values, which is referred to as the face lifting template in this embodiment.
In this embodiment, the trained face-lifting detection model may include a plurality of face-lifting templates, and each face-lifting template has at least one face-lifting portion. For example, the eyes in one face-lift template are face-lifted, the nose in one face-lift template is face-lifted, the eyes and nose in one face-lift template are face-lifted, and so on.
And each face-lifting template corresponds to one second feature data, the face-lifting detection model can calculate the similarity between the first feature data and each second feature data, and the face-lifting template corresponding to the second feature data with the maximum similarity is determined as the face-lifting template matched with the first feature data.
And step 204, when a face-lifting template matched with the first characteristic data exists in the template library, generating a first detection result for indicating face lifting of the user through the face-lifting detection model.
And step 205, obtaining the information of the face-lifting part marked in the face-lifting template through the face-lifting detection model, wherein the face-lifting part information is used for indicating the face-lifting part in the face-lifting image.
For example, if the eyes in one face-lift template are face-lifted, the face-lift part information marked in the face-lift template is the eyes.
And step 206, calculating the face-lifting reliability of each part in the face image according to the face-lifting part information and the first characteristic data through the face-lifting detection model.
In this embodiment, the first feature data may also be marked by using a matching face-lifting template, so that the marked face-lifting points (i.e., face-lifting part information) are included in the marked first feature data, and then face-lifting reliability of each part of the face is calculated.
After the face-lifting part is determined, the face-lifting detection model can utilize a detailed face-lifting point algorithm to calculate the face-lifting reliability of the face-lifting part in the first characteristic data, and utilize a rough face-lifting point algorithm to calculate the face-lifting reliability of other parts in the first characteristic data, so that the calculation efficiency is improved.
And step 207, generating a second detection result according to the face-lifting reliability of each part through the face-lifting detection model.
The face-lifting detection model may set a predetermined threshold in advance, compare the face-lifting reliability of each region with the predetermined threshold, determine a region corresponding to the face-lifting reliability higher than the predetermined threshold as a face-lifting region, and generate a second detection result indicating the face-lifting region.
And step 208, determining whether the user is face-lifting or not according to the first detection result output by the face-lifting detection model.
The face-lift detection model may output a first detection result, which may be used to indicate that the user is face-lift or not face-lift.
And 209, when the user performs face-lifting, determining at least one face-lifting part of the user according to a second detection result output by the face-lifting detection model, wherein the face-lifting part is a part in the face of the user.
It should be noted that, the face-lifting detection model may output a first detection result indicating that the user is not face-lifting when it is determined that the user is not face-lifting; alternatively, when the user's face-lifting is determined, a first detection result indicating the user's face-lifting and a second detection result indicating a face-lifting portion may be output; alternatively, the second detection result indicating the face-lifting part may be output when the face-lifting of the user is determined.
The embodiment can identify whether to perform face lifting or not through the face lifting detection model, thereby providing a new idea for face lifting identification.
To sum up, the face detection method provided by the embodiment of the present application detects a face image by obtaining the face image of a user and then detecting the face image through a face-lifting detection model obtained by training in advance, and the face-lifting detection model is obtained by training face images before and after face lifting of a plurality of users, so that the face-lifting detection model can detect whether the face in the face image is lifted, and a first detection result for indicating whether the user is lifted is generated, and thus, the face detection technology can be applied to the field of face-lifting identification, and the application range of the face detection technology is expanded.
Compared with the characteristic extraction of a single face image, the method has the advantages that the multidirectional characteristic extraction is carried out on a plurality of face images, the contingency of characteristic data can be reduced to a certain extent, and the accuracy of the characteristic data is improved.
Referring to fig. 3, a block diagram of a face detection apparatus according to an embodiment of the present application is shown, where the face detection apparatus may be applied to a face detection device. The face detection device may include:
an obtaining module 310, configured to obtain a face image of a user;
the detection module 320 is used for detecting the face images through a face-lifting detection model obtained by pre-training, wherein the face-lifting detection model is obtained by training the face images before and after face lifting of a plurality of users;
the determining module 330 is configured to determine whether the user is face-lifting according to the first detection result output by the face-lifting detection model.
In an optional embodiment, when the user performs face-lifting, the determining module 330 is further configured to determine at least one face-lifting part of the user according to the second detection result output by the face-lifting detection model, where the face-lifting part is a part in the face of the user.
In an optional embodiment, the detecting module 320 is further configured to:
performing feature extraction on the face image through a face-lifting detection model to obtain first feature data;
detecting whether a face-lifting template matched with the first characteristic data exists in a preset template library or not through a face-lifting detection model, wherein the face-lifting template is second characteristic data extracted from a face-lifting image containing at least one face-lifting part;
when a face-lifting template matched with the first feature data exists in the template library, generating a first detection result for indicating face lifting of the user through the face-lifting detection model.
In an alternative embodiment, when a face-lift template matching the feature data exists in the template library, the detecting module 320 is further configured to:
acquiring face-lifting part information marked in a face-lifting template through a face-lifting detection model, wherein the face-lifting part information is used for indicating face-lifting parts in a face-lifting image;
calculating the face-lifting credibility of each part in the face image according to the face-lifting part information and the first characteristic data through a face-lifting detection model;
and generating a second detection result according to the face-lifting credibility of each part through a face-lifting detection model.
In an optional embodiment, the detecting module 320 is further configured to:
when the face image comprises at least two face images with different shooting angles, extracting the characteristics of each face image through a face-lifting detection model;
and fusing the feature data of each identical part in all the face images through the face-lifting detection model to obtain first feature data, wherein the first feature data comprises the feature data of a plurality of parts in the face of the user.
In an optional embodiment, the obtaining module 310 is further configured to obtain a training sample set before the face image is detected by a face-lift detection model obtained through pre-training, where each training sample in the training sample set includes a face image of the same user before and after face lift and label information, where the label information is used to indicate at least one face-lift part in the face image;
the device also comprises a training module which is used for training the created model according to the training sample set to obtain the face-lifting detection model.
In an optional embodiment, the apparatus further comprises:
and the preprocessing module is used for preprocessing each face image in the training sample set before the training module trains the created face-lifting detection model according to the training set.
To sum up, the face detection device provided by the embodiment of the application detects the face image by acquiring the face image of the user and then by the face-lifting detection model obtained by pre-training, and the face-lifting detection model is obtained by training the face image before and after face lifting of a plurality of users, so that the face-lifting detection model can detect whether the face in the face image is lifted up or not, and a first detection result for indicating whether the face lifting is carried out or not is generated, therefore, the face detection technology can be applied to the field of face-lifting identification, and the application range of the face detection technology is expanded.
Compared with the characteristic extraction of a single face image, the method has the advantages that the multidirectional characteristic extraction is carried out on a plurality of face images, the contingency of characteristic data can be reduced to a certain extent, and the accuracy of the characteristic data is improved.
An embodiment of the present application provides a computer-readable storage medium, in which at least one instruction, at least one program, a set of codes, or a set of instructions is stored, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by a processor to implement the face detection method as described above.
An embodiment of the present application provides a face detection device, which includes a processor and a memory, where the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the face detection method as described above.
It should be noted that: in the face detection device provided in the above embodiment, when performing face detection, only the division of the functional modules is illustrated, and in practical application, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the face detection device is divided into different functional modules to complete all or part of the functions described above. In addition, the face detection device and the face detection method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments and are not described herein again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description should not be taken as limiting the embodiments of the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the embodiments of the present application.
Claims (10)
1. A face detection method, comprising:
acquiring a face image of a user;
detecting the face image through a face-lifting detection model obtained by pre-training, wherein the face-lifting detection model is obtained by training face images before and after face lifting of a plurality of users;
and determining whether the user is face-lifting or not according to a first detection result output by the face-lifting detection model.
2. The method of claim 1, wherein when the user is performing face-lifting, the method further comprises:
and determining at least one face-lifting part of the user according to a second detection result output by the face-lifting detection model, wherein the face-lifting part is a part in the face of the user.
3. The method of claim 2, wherein the face-lift detection model obtained by pre-training is used for detecting the face image, and comprises the following steps:
performing feature extraction on the face image through the face-lifting detection model to obtain first feature data;
detecting whether a face-lifting template matched with the first characteristic data exists in a preset template library or not through the face-lifting detection model, wherein the face-lifting template is second characteristic data extracted from a face-lifting image containing at least one face-lifting part;
when a face-lifting template matched with the first feature data exists in the template library, generating the first detection result for indicating the face lifting of the user through the face-lifting detection model.
4. The method of claim 3, wherein when a face-lift template matching the feature data exists in the template library, the method further comprises:
acquiring face-lifting part information marked in the face-lifting template through the face-lifting detection model, wherein the face-lifting part information is used for indicating face-lifting parts in the face-lifting image;
calculating the face-lifting credibility of each part in the face image according to the face-lifting part information and the first feature data through the face-lifting detection model;
and generating the second detection result according to the face-lifting credibility of each part through the face-lifting detection model.
5. The method of claim 3, wherein the extracting the features of the face image through the face-lifting detection model to obtain first feature data comprises:
when the face image comprises at least two face images with different shooting angles, extracting the characteristics of each face image through the face-lifting detection model;
and fusing the feature data of the same parts in all the face images through the face-lifting detection model to obtain the first feature data, wherein the first feature data comprises the feature data of a plurality of parts in the face of the user.
6. The method according to any one of claims 1 to 5, wherein before the face image is detected by the pre-trained face-lift detection model, the method further comprises:
acquiring a training sample set, wherein each training sample in the training sample set comprises a face image and mark information of the same user before and after face-lifting, and the mark information is used for indicating at least one face-lifting part in the face image;
and training the created model according to the training sample set to obtain the face-lifting detection model.
7. The method of claim 6, wherein prior to said training the created cosmetic detection model according to the training set, the method further comprises:
and preprocessing each face image in the training sample set.
8. An apparatus for face detection, the apparatus comprising:
the acquisition module is used for acquiring a face image of a user;
the face detection module is used for detecting the face images through a face-lifting detection model obtained by pre-training, and the face-lifting detection model is obtained by training the face images before and after face lifting of a plurality of users;
and the determining module is used for determining whether the user is face-lifting or not according to a first detection result output by the face-lifting detection model.
9. A computer-readable storage medium, having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement a face detection method according to any one of claims 1 to 7.
10. A face detection device, characterized in that the face detection device comprises a processor and a memory, wherein the memory has stored therein at least one instruction, which is loaded and executed by the processor to implement the face detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010243467.4A CN111428670B (en) | 2020-03-31 | 2020-03-31 | Face detection method, face detection device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010243467.4A CN111428670B (en) | 2020-03-31 | 2020-03-31 | Face detection method, face detection device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428670A true CN111428670A (en) | 2020-07-17 |
| CN111428670B CN111428670B (en) | 2022-08-09 |
Family
ID=71550121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010243467.4A Active CN111428670B (en) | 2020-03-31 | 2020-03-31 | Face detection method, face detection device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428670B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396117A (en) * | 2020-11-24 | 2021-02-23 | 维沃移动通信有限公司 | Image detection method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529445A (en) * | 2016-10-27 | 2017-03-22 | 珠海市魅族科技有限公司 | Makeup detection method and apparatus |
| CN108447017A (en) * | 2018-05-31 | 2018-08-24 | Oppo广东移动通信有限公司 | Face virtual face-lifting method and device |
| US20190095764A1 (en) * | 2017-09-26 | 2019-03-28 | Panton, Inc. | Method and system for determining objects depicted in images |
| CN110889376A (en) * | 2019-11-28 | 2020-03-17 | 创新奇智(南京)科技有限公司 | Safety helmet wearing detection system and method based on deep learning |
-
2020
- 2020-03-31 CN CN202010243467.4A patent/CN111428670B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529445A (en) * | 2016-10-27 | 2017-03-22 | 珠海市魅族科技有限公司 | Makeup detection method and apparatus |
| US20190095764A1 (en) * | 2017-09-26 | 2019-03-28 | Panton, Inc. | Method and system for determining objects depicted in images |
| CN108447017A (en) * | 2018-05-31 | 2018-08-24 | Oppo广东移动通信有限公司 | Face virtual face-lifting method and device |
| CN110889376A (en) * | 2019-11-28 | 2020-03-17 | 创新奇智(南京)科技有限公司 | Safety helmet wearing detection system and method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| YANG MH: "《IEEE Transactions on Pattern Analysis and Machine Intelligence》", 30 December 2002 * |
| 徐庆等: "一种基于特征模型的人脸检测方法", 《计算机工程与应用》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396117A (en) * | 2020-11-24 | 2021-02-23 | 维沃移动通信有限公司 | Image detection method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428670B (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | Fingerprint liveness detection using an improved CNN with image scale equalization | |
| CN108921100B (en) | Face recognition method and system based on visible light image and infrared image fusion | |
| US10049262B2 (en) | Method and system for extracting characteristic of three-dimensional face image | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| US7873189B2 (en) | Face recognition by dividing an image and evaluating a similarity vector with a support vector machine | |
| Ranjan et al. | Unconstrained age estimation with deep convolutional neural networks | |
| CN109376604B (en) | Age identification method and device based on human body posture | |
| Singh et al. | Face recognition using facial symmetry | |
| Emeršič et al. | Pixel-wise ear detection with convolutional encoder-decoder networks | |
| CN106650574A (en) | Face identification method based on PCANet | |
| CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
| CN106874877A (en) | A kind of combination is local and global characteristics without constraint face verification method | |
| CN110599187A (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| CN110598574A (en) | Intelligent face monitoring and identifying method and system | |
| TW201828156A (en) | Image identification method, measurement learning method, and image source identification method and device capable of effectively dealing with the problem of asymmetric object image identification so as to possess better robustness and higher accuracy | |
| CN117095436A (en) | Intelligent management system and method for enterprise employee information | |
| Bharadi et al. | Multi-instance iris recognition | |
| Silva et al. | POEM-based facial expression recognition, a new approach | |
| Geetha et al. | 3D face recognition using Hadoop | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| Reddy et al. | Comparison of HOG and fisherfaces based face recognition system using MATLAB | |
| Jatain et al. | Automatic human face detection and recognition based on facial features using deep learning approach | |
| Mohammad | Multi-Modal Ocular Recognition in Presence of Occlusion in Mobile Devices | |
| CN114743249B (en) | Recognition model training method, micro-expression recognition method, device, equipment and medium | |
| Mishra et al. | Integrating State-of-the-Art Face Recognition and Anti-Spoofing Techniques into Enterprise Information Systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 210000 Longmian Avenue 568, High-tech Park, Jiangning District, Nanjing City, Jiangsu Province Patentee after: Xiaoshi Technology (Jiangsu) Co.,Ltd. Address before: 210000 Longmian Avenue 568, High-tech Park, Jiangning District, Nanjing City, Jiangsu Province Patentee before: NANJING ZHENSHI INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |